Contact : 9561854529 Email : submitpaper@ijaea.com editorinchief.ijaea@gmail.com Working Hours: 9am to 9PM

International Journal of Advanced Engineering Application

ISSN: 3048-6807

Submit Paper Apply for Reviewer

Comparative Study on Performance of Various Neural Network Algorithms in Construction Project Cost Prediction

Author(s):Kumar Rajan1,Subham Reddy R2

Affiliation: 1,2Department Of Computer Science Engineering. 1,2Sphoorthy Engineering College, Telangana, India.

Page No: 1-4

Volume issue & Publishing Year: Volume 1 Issue 6, OCT-2024

Journal: International Journal of Advanced Engineering Application (IJAEA)

ISSN NO: 3048-6807

DOI:

Download PDF

Abstract:
Accurate prediction of construction costs is essential to ensure smooth project execution and guarantee economic benefits. The primary objective of this study is to explore the application of neural network algorithms in predicting construction project costs. Specifically, a back-propagation neural network (BPNN) enhanced with the AdaBoost algorithm was tested and compared with traditional BPNN and support vector machine (SVM) models. Simulation results indicated that the AdaBoost-BPNN algorithm converged faster with a smaller mean square error, providing a more accurate prediction (MAE: 0.467, RMSE: 1.118). This study offers valuable insights into the advantages of boosting techniques in neural network models for cost prediction in construction projects.

Keywords: Neural networks, Construction cost prediction, AdaBoost, BPNN, SVM.

Reference:

  • [1] Y. G. Abed, T. Hasan, R. Zehawi, and Z. Kamil, “Machine learning algorithms for constructions cost prediction: A systematic review,” Int. J. Nonlinear Anal. Appl., vol. 13, no. 2, pp. 2205–2218, 2022.
  • [2] F. C. Cevik, B. Gever, N. Tak, and T. Khaniyev, “Forecast combination approach with meta-fuzzy functions for forecasting the number of immigrants within the maritime line security project in Turkey,” Soft Comput., vol. 27, no. 5, pp. 2509–2535, 2023, doi: 10.1007/s00500-022-07800-7.
  • [3] J. Dong, Y. Chen, and G. Guan, “Cost index predictions for construction engineering based on LSTM neural networks,” Adv. Civ. Eng., vol. 2020, no. 4, pp. 1–14, 2020, doi: 10.1155/2020/6518147.
  • [4] S. A. M. Faghih, Y. Gholipour, and H. Kashani, “Time series analysis framework for forecasting the construction labor costs,” KSCE J. Civ. Eng., vol. 25, no. 8, pp. 2809–2823, 2021, doi: 10.1007/s12205-021-1489-4.
  • [5] S. T. Hashemi, O. M. Ebadati, and H. Kaur, “Cost estimation and prediction in construction projects: A systematic review on machine learning techniques,” SN Appl. Sci., vol. 2, no. 10, p. 1703, 2020, doi: 10.1007/s42452-020-03497-1.
  • [6] O. N. Kalinina, “Developing the process of value estimation and modeling the project cost,” Vestnik Plekhanov Russ. Univ. Econ., no. 3, pp. 110–123, 2020, doi: 10.21686/2413-2829-2020-3-110-123.
  • [7] Y. Kawahara, S. Muto, K. Nishida, Y. Ito, and Y. Kobayashi, “Water demand forecast and cost analysis for water infrastructure maintenance,” J. Jpn. Soc. Civ. Eng., Ser. D3, vol. 77, no. 5, pp. 193–202, 2022, doi: 10.2208/jscejipm.77.5_I_193.
  • [8] V. Kumar, S. Singla, and A. Bansal, “A review on machine learning algorithms for cost estimation in construction projects,” in Proc. Int. Conf. Intelligent Computing & Optimization, Springer, 2023, pp. 209–216, doi: 10.1007/978-3-031-36246-0_20.
  • [9] Y. Lavi and J. Apt, “Load forecast uncertainties can affect transmission expansion decisions,” Electr. Power Syst. Res., vol. 226, p. 109959, 2024.
  • [10] J. Li and Z. Sun, “Cost stickiness, earnings forecast accuracy, and the informativeness of stock prices about future earnings: Evidence from China,” Humanit. Soc. Sci. Commun., vol. 10, no. 1, pp. 1–16, 2023, doi: 10.1057/s41599-023-01592-3.
  • [11] N. Li, X. Wang, C. Li, Z. Zhang, and W. Zhang, “The overhauls technical innovation project optimization method of power grid device based on life cycle asset management,” Energy Rep., vol. 6, pp. 1249–1254, 2020, doi: 10.1016/j.egyr.2020.11.047.
  • [12] Q. Li, G. Chen, Z. Li, and B. Fan, “Forecast of development cost of missile equipment based on partial least squares,” in J. Phys.: Conf. Ser., vol. 1650, no. 3, p. 032162, IOP Publishing, 2020, doi: 10.1088/1742-6596/1650/3/032162.
  • [13] A. Nouh, E. Elkasaby, and K. Hussein, “Establishment of prediction system for cost of defect liability phase in construction project,” Constr. Innov., vol. 23, no. 2, pp. 467–486, 2023, doi: 10.1108/CI-05-2021-0096.
  • [14] M. H. Rafiei and H. Adeli, “Novel machine-learning model for estimating construction costs considering economic variables and indexes,” J. Constr. Eng. Manage., vol. 144, no. 12, p. 04018106, 2018.
  • [15] S. Saeidlou and N. Ghadiminia, “A construction cost estimation framework using DNN and validation unit,” Build. Res. Inf., vol. 52, no. 1–2, pp. 38–48, 2024.
  • [16] X. Shi et al., “Research on the method of power grid equipment material price forecast based on grey theory,” in E3S Web Conf., vol. 213, p. 03018, 2020, doi: 10.1051/e3sconf/202021303018.
  • [17] M. Wang, X. Qi, P. Geng, L. An, and J. Wang, “Transmission technical project investment forecasting under the high-dimension small sample conditions,” in IOP Conf. Ser.: Mater. Sci. Eng., vol. 768, no. 6, p. 062065, 2020, doi: 10.1088/1757-899X/768/6/062065.
  • [18] D. Ye, “An algorithm for construction project cost forecast based on particle swarm optimization-guided BP neural network,” Sci. Program., vol. 2021, p. 4309495, 2021, doi: 10.1155/2021/4309495.
  • [19] H. Zahoor, R. M. Khan, A. Nawaz, M. Ayaz, and A. Maqsoom, “Project control and forecast assessment of building projects in Pakistan using earned value management,” Eng. Constr. Archit. Manage., vol. 29, no. 2, pp. 842–869, 2022, doi: 10.1108/ECAM-11-2020-0989.
  • [20] M. Zhao and X. Zi, “Using earned value management with exponential smoothing technique to forecast project cost,” in J. Phys.: Conf. Ser., vol. 1955, no. 1, p. 012101, 2021, doi: 10.1088/1742-6596/1955/1/012101.
  • [21] M. Zhou et al., “Research on the forecast model of transmission and distribution project cost based on support vector regression algorithm,” in IOP Conf. Ser.: Earth Environ. Sci., vol. 714, no. 4, p. 042009, 2021, doi: 10.1088/1755-1315/714/4/042009